Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 11461
    Prev
    Next
    INDEX
    Explanations

    financial or budget-related terms and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    okane
    -0.06
    ickle
    -0.06
    ontrol
    -0.06
    pires
    -0.06
    umpt
    -0.06
    /Foundation
    -0.06
    edm
    -0.06
    olist
    -0.06
    udes
    -0.05
    umbs
    -0.05
    POSITIVE LOGITS
    stand
    0.12
     normal
    0.11
     current
    0.11
    lying
    0.10
     previous
    0.10
     terms
    0.10
     questioning
    0.09
     present
    0.09
    staff
    0.09
    min
    0.09
    Activations Density 0.014%

    No Known Activations